Model comparison
Mistral vs Mistral Small 3
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Mistral scores higher in 3 categories and Mistral Small 3 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Mistral Small 3 leads 63.7 to 52.6.
- Mistral Small 3 has downloadable open weights; the other is API-only.
Side by side
| Mistral | Mistral Small 3 | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 29.9 | 31.2 |
| Released | — | 2025-01-30 |
| Weights | Proprietary | Open |
| Context window | — | 33K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.05 |
| Output $ / M tokens | — | $0.08 |
| Results tracked | 22 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral: 33.8 (#250), Mistral Small 3: 36.5 (#207)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1162 | 1246 |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
Reasoning Mistral leads
Mistral: 22.2 (#200), Mistral Small 3: 18.9 (#273)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1233 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math Mistral leads
Mistral: 22.3 (#278), Mistral Small 3: 16.3 (#295)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1180 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| Omni-MATH | 7.2% | — |
Knowledge Mistral Small 3 leads
Mistral: 16.6 (#288), Mistral Small 3: 25.1 (#263)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1125 | 1202 |
| GPQA Diamond | — | 47.3% |
| MMLU-Pro | 27.7% | — |
| Confabulations | — | 25.2% |
| GPQA (HELM) | 30.3% | — |
Multilingual Mistral Small 3 leads
Mistral: 32.8 (#254), Mistral Small 3: 37.3 (#236)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1129 | 1198 |
| LMArena Chinese | 1109 | 1204 |
| LMArena French | 1180 | 1203 |
| LMArena German | 1155 | 1211 |
| LMArena Japanese | 1013 | 1111 |
| LMArena Korean | 1032 | 1188 |
| LMArena Russian | 1168 | 1216 |
| LMArena Spanish | 1143 | — |
Instruction Following Mistral Small 3 leads
Mistral: 52.6 (#288), Mistral Small 3: 63.7 (#229)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1152 | 1214 |
| IFEval | 56.8% | — |
Long Context Mistral Small 3 leads
Mistral: 35.0 (#245), Mistral Small 3: 37.8 (#211)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1153 | 1246 |
Writing & Preference Mistral leads
Mistral: 37.0 (#260), Mistral Small 3: 32.2 (#280)
| Benchmark | Mistral | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1165 | 1234 |
| LMArena Creative Writing | 1158 | 1195 |
| LMArena Multi-Turn | 1147 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Mistral Small 3?
Mistral Small 3 is the stronger model overall, scoring 31.2 to 29.9 on the Noometry Index.
Is Mistral or Mistral Small 3 better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 33.8 in the Noometry coding category.
How many benchmarks do Mistral and Mistral Small 3 share?
16 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Mistral Small 3 has 24.